Automating the Evolution of Agent Communication Languages Using Negotiation

本研究旨在理解和自动化语言在开放、异构和分布式环境中相互作用的人工的、基于知识的和理性的代理中出现的机制。其目的是设计和实现这样的代理：当遇到不共享代理通信语言的其他代理时，能够发起创建并进一步发展和丰富一种相互理解的通信语言。这项研究的新颖之处在于，它使智能体能够自行发展和发展通过共同语言进行交流的能力，而不是依赖于设计者预先设计并内置到智能体中的这种能力。本研究得到了两个研究流的支持：1)理性的、具有社会能力的人工智能体的设计；2)博弈论中发展起来的、人工智能研究中自动化的谈判机制。这项工作将有助于异构和开放多智能体系统的基础研究，现实环境中人工智能体之间的有效通信，实际多智能体系统设计以及本科生和研究生的培训。

This research aims to understand and automate the mechanisms by which language can emerge among artificial, knowledge-based and rational agents that interact in open, heterogeneous, and distributed environments. The intent is to design and implement agents that, upon encountering other agent(s) with which they do not share an agent communication language, are able to initiate creation of, and further are able to evolve and enrich, a mutually understandable communication language. The novelty of this research is that it enables the agents to develop and evolve, on their own, the capacity of communicating via a common language, as opposed to relying on this ability to be pre-designed and built into the agents by their designers. This research is supported by two streams of research, 1) the design of rational, socially competent artificial agents, and 2) the mechanism of negotiation as developed in game theory and automated in artificial intelligence research. This work will contribute to fundamental research in heterogeneous and open multiagent systems, effective communication among artificial agents in realistic settings, practical multiagent system design and the training of undergraduate and graduate students.